Labeling Density Research Articles

TDOcc: Exploit machine learning and big data in multi-view 3D occupancy prediction

With the advancement of machine learning and big data technologies, BEV(Bird’s Eye View)-based methodologies have recently achieved significant breakthroughs in multi-view 3D occupancy prediction tasks. However, BEV(Bird’s Eye View)-centric 3D occupancy prediction continues to grapple with feature representation and annotation costs when applied to complex open environments. In order to surmount these issues and further propel the evolution of 3D occupancy tasks, this study introduces a novel framework termed TDOcc. By leveraging multi-camera imagery, TDOcc executes 3D semantic occupancy prediction by directly learning from unprocessed 3D spaces, thereby maximizing information retention. TDOcc presents two notable advantages: firstly, it utilizes dense occupancy labels, which not only facilitate robust dense occupancy inference but also enable comprehensive object estimation within the scene. Secondly, the framework synthesizes historical feature information by adeptly aligning past and present features through temporal cues, thereby bolstering the efficacy of the feature fusion module. Additionally, with a view to address the ill-posed nature inherent in camera-based 3D occupancy prediction, we incorporate an enhancement module that operates within the 3D feature space. This module has been meticulously crafted for the training phase to amplify the model’s learning potential. Extensive experiments conducted on the widely recognized nuScenes dataset underscore the efficacy of our proposed approach. Compared to the most recent TPVFormer and OccFormer, our approach has achieved a significant improvement in mean Intersection over Union (mIoU) by 2.0 and 0.8 respectively, and has reached performance comparable to the state-of-the-art LiDAR-based methods.

Ultrastructural characterization of hippocampal inhibitory synapses under resting and stimulated conditions.

The present study uses electron microscopy to document ultrastructural characteristics of hippocampal GABAergic inhibitory synapses under resting and stimulated conditions in three experimental systems. Synaptic profiles were sampled from stratum pyramidale and radiatum of the CA1 region from (1) perfusion fixed mouse brains, (2) immersion fixed rat organotypic slice cultures, and from (3) rat dissociated hippocampal cultures of mixed cell types. Synapses were stimulated in the brain by a 5min delay in perfusion fixation to trigger an ischemia-like excitatory condition, and by treating the two culture systems with 90 mM high K+ for 2-3min to depolarize the neurons. Upon such stimulation conditions, the presynaptic terminals of the inhibitory synapses exhibited similar structural changes to those seen in glutamatergic excitatory synapses, with depletion of synaptic vesicles, increase of clathrin-coated vesicles and appearance of synaptic spinules. However, in contrast to excitatory synapses, no structural differences were detected in the postsynaptic compartment of the inhibitory synapses upon stimulation. There were no changes in the appearance of material associated with the postsynaptic membrane or the length and curvature of the membrane. Also no change was detected in the labeling density of gephyrin, a GABAergic synaptic marker, lining the postsynaptic membrane. Furthermore, virtually all inhibitory synaptic clefts remained rigidly apposed, unlike in the case of excitatory synapses where ~ 20-30% of cleft edges were open upon stimulation, presumably to facilitate the clearance of neurotransmitters from the cleft. The fact that no open clefts were induced in inhibitory synapses upon stimulation suggests that inhibitory input may not need to be toned down under these conditions. On the other hand, similar to excitatory synapse, EGTA (a calcium chelator) induced open clefts in ~ 18% of inhibitory synaptic cleft edges, presumably disrupting similar calcium-dependent trans-synaptic bridges in both types of synapses.

Dopamine loss alters glutamate synapses and transporters in the medial prefrontal cortex and anxiety-related behaviour in a male MPTP rodent model of Parkinson's disease.

Anxiety is a prominent non-motor symptom of Parkinson's disease (PD). Changes in the B-spectrum recordings in PD patients of the prefrontal cortex correlate with increased anxiety. Using a rodent model of PD, we reported alterations in glutamate synapses in the striatum and substantia nigra following dopamine (DA) loss. We hypothesize that DA loss will result in increased anxiety-related behaviours and that this will be associated with alterations in glutamate synapses and transporters within the medial prefrontal cortex (mPFC). Following 4weeks of progressive 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP) administration, there was an increase in anxiety-related behaviours and a 78% decrease in plasma corticosterone levels versus the vehicle (VEH)-treated mice. This was associated with a 30% decrease in the density of dendritic spines in Layers Il/Ill, and a 53% decrease in the density of glutamate immuno-gold labelling within vesicular glutamate transporter 1 (Vglut1)-labelled nerve terminals and spines, with no change within vesicular glutamate transporter 2 (Vglut2) positive terminals/spines in the MPTP versus VEH groups. Our prior work determined that a decrease in striatal glutamate terminal density was associated with an increase in extracellular glutamate levels. There was an increase in protein expression of Vglut1 (40%), Vglut2 (37%) and glutamate aspartate transporter (GLAST) (225%), and a decrease in glutamate transporter 1 (GLT-1) (50%) and excitatory amino acid carrier 1 (EAAC1) (51%), in the MPTP versus VEH groups within the mPFC. These data suggest that the decrease in dendritic spines within the mPFC following nigrostriatal DA loss may be due to increased extracellular glutamate levels (decrease in glutamate transporters), leading to an increase in anxiety-related behaviours.

Soft-label recover based label-specific features learning

Presently, multi-label classification algorithms are mainly based on positive and negative logical labels, which have achieved good results. However, logical labeling inevitably leads to the label misclassification problem. In addition, missing labels are common in multi-label datasets. Recovering missing labels and constructing soft labels that reflect the mapping relationship between instances and labels is a difficult task. Most existing algorithms can only solve one of these problems. Based on this, this paper proposes a soft-label recover based label-specific features learning (SLR-LSF) to solve the above problems simultaneously. Firstly, the information entropy is used to calculate the confidence matrix between labels, and the membership degree of soft labels is obtained by combining the label density information. Secondly, the membership degree and confidence matrix are combined to construct soft labels, and this process not only solves the problem of missing labels but also obtains soft labels with richer semantic information. Finally, in the process of learning specific label features for soft labels. The local smoothness of the labels learned through stream regularization is complemented by the global label correlation, thus improving the classification performance of the algorithm. To demonstrate the effectiveness of the proposed algorithm, we conduct comprehensive experiments on several datasets.

Advancing robots with greater dynamic dexterity: A large-scale multi-view and multi-modal dataset of human-human throw&catch of arbitrary objects

Learning and imitating behavioral intelligence from human demonstrations is a promising approach towards the intuitive programming of robots for enhanced dynamic dexterity. However, there has been no publicly available dataset in this domain. To address this gap, we introduce the first large-scale dataset and recording framework specifically designed for studying human collaborative dynamic dexterity in throw&catch tasks. The dataset, named H2TC, contains 15,000 multi-view and multi-modal synchronized recordings of diverse Human-Human Throw-and-Catch activities. It involves 34 human subjects with typical motor abilities and a variety of 52 objects frequently manipulated through throw&catch in domestic and/or industrial scenarios. The dataset is supplemented with a hierarchy of manually annotated semantic and dense labels, such as the ground truth human body, hand and object motions captured with specialized high-precision motion tracking systems. These rich annotations make the dataset well-suited for a wide range of robot studies, including both low-level motor skill learning and high-level cognitive planning and recognition. We envision that the proposed dataset and recording framework will facilitate learning pipelines to extract insights on how humans coordinate both intra- and interpersonally to throw and catch objects, ultimately leading to the development of more capable and collaborative robots. The dataset, along with a suite of utility tools, such as those for visualization and annotation, can be accessed from our project page at https://h2tc-roboticsx.github.io/ .

Iterative Immunostaining and NEDD Denoising for Improved Signal-To-Noise Ratio in ExM-LSCM.

Expansion microscopy (ExM) has significantly reformed the field of super-resolution imaging, emerging as a powerful tool for visualizing complex cellular structures with nanoscale precision. Despite its capabilities, the epitope accessibility, labeling density, and precision of individual molecule detection pose challenges. We recently developed an iterative indirect immunofluorescence (IT-IF) method to improve the epitope labeling density, improving the signal and total intensity. In our protocol, we iteratively apply immunostaining steps before the expansion and exploit signal processing through noise estimation, denoising, and deblurring (NEDD) to aid in quantitative image analyses. Herein, we describe the steps of the iterative staining procedure and provide instructions on how to perform NEDD-based signal processing. Overall, IT-IF in ExM-laser scanning confocal microscopy (LSCM) represents a significant advancement in the field of cellular imaging, offering researchers a versatile tool for unraveling the structural complexity of biological systems at the molecular level with an increased signal-to-noise ratio and fluorescence intensity. Key features • Builds upon the method developed by Mäntylä et al. [1] and introduces the IT-IF method and signal-processing platform for several nanoscopy imaging applications. • Retains signal-to-noise ratio and significantly enhances the fluorescence intensity of ExM-LSCM data. • Automatic estimation of noise, signal reconstruction, denoising, and deblurring for increased reliability in image quantifications. • Requires at least seven days to complete.

Deep Mouse Brain Two-Photon Near-Infrared Fluorescence Imaging Using a Superconducting Nanowire Single-Photon Detector Array.

Two-photon microscopy (2PM) has become an important tool in biology to study the structure and function of intact tissues in vivo. However, adult mammalian tissues such as the mouse brain are highly scattering, thereby putting fundamental limits on the achievable imaging depth, which typically reside at around 600-800 μm. In principle, shifting both the excitation as well as (fluorescence) emission light to the shortwave near-infrared (SWIR, 1000-1700 nm) region promises substantially deeper imaging in 2PM, yet this shift has proven challenging in the past due to the limited availability of detectors and probes in this wavelength region. To overcome these limitations and fully capitalize on the SWIR region, in this work, we introduce a novel array of superconducting nanowire single-photon detectors (SNSPDs) and associated custom detection electronics for use in near-infrared 2PM. The SNSPD array exhibits high efficiency and dynamic range as well as low dark-count rates over a wide wavelength range. Additionally, the electronics and software permit a seamless integration into typical 2PM systems. Together with an organic fluorescent dye emitting at 1105 nm, we report imaging depth of >1.1 mm in the in vivo mouse brain, limited mostly by available labeling density and laser properties. Our work establishes a promising, and ultimately scalable, new detector technology for SWIR 2PM that facilitates deep tissue biological imaging.

A Second Look at Label Density in Large-Scale Online Maps

A Second Look at Label Density in Large-Scale Online Maps

Multifunctional intelligent indication labels featuring antibacterial properties based on pectin/carboxymethyl chitosan incorporated with porous microspheres loaded with anthocyanins: A new approach for salmon preservation and freshness detection

Multifunctional intelligent indication labels tend to prolong the quality guarantee period and monitor the freshness of food. In this study, indication labels were prepared with carboxymethyl chitosan (CMCS) and pectin as substrate, and porous microspheres loaded with anthocyanins (ACN@PGMs) as indicators and antioxidant as well as clove essential oil as an antibacterial agent. The interaction between pectin and CMCS and the addition of ACN@PGMs improved the physical properties and structural density of indication labels due to electrostatic complexing and hydrogen-bonding interactions, which exhibited optimal performance when the added anthocyanins equivalent was 0.25 mg/mL. Meanwhile, the water contact angle and antibacterial activity reached maximum values of 78.8 ± 2.3°, 11.8 ± 0.88 cm (E.coli), and 17.00 ± 0.71 cm (S.aureus), respectively. In addition, indication labels displayed sensitive color responses to different pH and ammonia environments. In application, labels could extend the shelf life of refrigerated salmon from 4 days to 9 days and showed significant color changes when salmon spoiled. Overall, indication labels played a positive role in extending shelf life and visual freshness detection, which could be employed in food quality evaluation and food preservation.

Selective disruption of synaptic NMDA receptors of the hippocampal trisynaptic circuit in Aβ pathology

Synaptic dysfunction is an early feature in Alzheimer’s disease (AD) pathogenesis and a major morphological correlate of memory deficits. Given the main synaptic location of N-methyl-D-aspartate receptors (NMDARs), their dysregulation has been implicated in these pathological effects. Here, to detect possible alterations in the expression and synaptic localisation of the GluN1 subunit in the brain of amyloidogenic APP/PS1 mice, we employed histoblot and SDS-digested freeze-fracture replica labelling (SDS-FRL) techniques. Histoblots showed that GluN1 expression was significantly reduced in the hippocampus in a layer-dependent manner, in the cortex and the caudate putamen of APP/PS1 transgenic mice at 12 months of age but was unaltered at 1 and 6 months. Using quantitative SDS-FRL, we unravelled the molecular organisation of GluN1 in seven excitatory synapse populations at a high spatial resolution in the CA1 and CA3 fields and the DG of the hippocampus in 12-month-old APP/PS1 mice. In the CA1 field, the labelling density for GluN1 in the excitatory synapses established on spines and interneurons, was significantly reduced in APP/PS1 mice compared to age-matched wild-type mice in the stratum lacunosum-moleculare but unaltered in the stratum radiatum. In the CA3 field, synaptic GluN1 was reduced in mossy fibre-CA3 pyramidal cell synapses but unaltered in the A/C-CA3 pyramidal cell synapses. In the DG, the density of GluN1 in granule cell-perforant pathway synapses was reduced in APP/PS1 mice. Altogether, our findings provide evidence of specific alterations of synaptic GluN1 in the trisynaptic circuit of the hippocampus in Aβ pathology. This differential vulnerability in the disruption of NMDARs may be involved in the mechanisms causing abnormal network activity of the hippocampal circuit and cognitive impairment characteristic of APP/PS1 mice.

Downstream lingering attention transformer network (DsLATNet) for land use land cover classification: A bicolor deep learning framework

Land Use and Land Cover (LULC) classification is the process of locating and classifying regions of the Earth's surface (land cover) based on their physical attributes and human utilization (land use purpose). It is essential for mapping and monitoring changes in ecosystems, facilitating effective resource management and informed decision-making in land-use planning. Convolutional Neural Network (CNN’s) is incapable of capturing long-range dependencies. The effectiveness of transformers relies on extensive training datasets, yet many satellite datasets have comparatively limited sample sizes. Moreover, due to the numerous factors influencing visual prominence, it is challenging to obtain abundant features from a single-color space. To overcome these limitations, we introduce an innovative bicolor architecture Downstream Lingering Attention Transformer Network (DsLATNet). DsLATNet characterizes remote sensing images on two color spaces viz RGB and HSV by processing the information using Residual Network −50(ResNet-50) backbone network.Extracted features of backbone network are further refined to acquire detailed aware features through Downstream Lingering Feature Pyramid Network (DsLFPN).This is further integrated with a DuoTransformer that utilizes attention mechanisms to obtain long-range dependencies. Eventually, the features are aggregated using residual connections that are dilated in-depth multiple times to produce class labels. The efficacy of the algorithm is evaluated through standard classification accuracy metrics. Experimental results on both the Wuhan Dense Labeling Dataset (WHDLD) and the Gaofen Image Dataset (GID) exhibit that the suggested technique exceeds cutting-edge classification methods. WHDLD achieved an Overall Accuracy (OA) of 86.34 %, Average Accuracy (AA) of 75.62 %, and Kappa coefficient (K) of 80.75, while the GID exhibited superior performance with an OA of 86.43 %, AA of 88.13 %, and K of 81.25.

Immunochromatographic Strip Based on Tetrahedral DNA Immunoprobe for the Detection of Aflatoxin B1 in Rice Bran Oil.

Aflatoxin B1 (AFB1), a widespread contaminant in food and feeds, poses a threat to the health of animals and humans. Consequently, it is significant to develop a rapid, precise and highly sensitive analytical method for the detection of AFB1. Herein, we developed an immunochromatographic strip (ICS) based on a tetrahedral DNA (TDN) immunoprobe for AFB1 determination in rice bran oil. Three sizes of TDN immunoprobes (AuNP-TDN13bp-mAb, AuNP-TDN17bp-mAb, AuNP-TDN26bp-mAb) were constructed, and the performance of these three immunoprobes, including the effective antibody labeling density and immunoaffinity, was measured and compared with that of the immunoprobe (AuNP-mAb) developed using the physical adsorption method. Subsequently, the optimal TDN immunoprobe, namely AuNP-TDN13bp-mAb, was selected to prepare the immunochromatographic strip (ICS) for the qualitative and quantitative detection of AFB1 in rice bran oil. The visual limits of detection (vLODs) of the ICS based on AuNP-TDN13bp-mAb and AuNP-mAb were 0.2 ng/mL and 2 ng/mL, with scanning quantitative limits (sLOQs) of 0.13 ng/mL and 1.4 ng/mL, respectively. The ICS demonstrated a wide linear range from 0.02 ng/mL to 0.5 ng/mL, with good specificity, accuracy, precision, repeatability, and stability. Moreover, a high consistency was observed between the constructed ICS and ultra-high-performance liquid chromatography (UPLC) in the quantification of AFB1. The results indicated that the introduction of TDN was beneficial for promoting efficient antibody labeling, protecting the bioactivity of immunoprobes, and increasing the sensitivity of detection, which would provide new perspectives for the achievement of the highly sensitive detection of mycotoxins.

Structure-aware sign language recognition with spatial–temporal scene graph

Continuous sign language recognition (CSLR) is essential for the social participation of deaf individuals. The structural information of sign language motion units plays a crucial role in semantic representation. However, most existing CSLR methods treat motion units as a whole appearance in the video sequence, neglecting the exploitation and explanation of structural information in the models. This paper proposes a Structure-Aware Graph Convolutional Neural Network (SA-GNN) model for CSLR. This model constructs a spatial–temporal scene graph, explicitly capturing motion units’ spatial structure and temporal variation. Furthermore, to effectively train the SA-GNN, we propose an adaptive bootstrap strategy that enhances weak supervision using dense pseudo labels. This strategy incorporates a confidence cross-entropy loss to adjust the distribution of pseudo labels adaptively. Extensive experiments validate the effectiveness of our proposed method, achieving competitive results on popular CSLR datasets.

Palladium‐Catalyzed Sc(OTf)3/Cs2CO3‐Assisted C−O Cross‐Coupling of Vinylidenecyclopropane‐Diesters with Phenolic Compounds

AbstractWe herein describe a method in the synthesis of aryl ether derivatives from a cross‐coupling reaction of vinylidenecyclopropane‐diesters (VDCP‐diesters) with commercially available phenolic compounds for the formation of C−O bond under palladium catalysis and assisted by Sc(OTf)3/Cs2CO3. This developed transformation proceeds through a nucleophilic addition at the 2‐position of allenic moiety at 50 °C for 4.0 h and is compatible with substituents such as bromine, iodine and borate on the phenolic substrates via a zwitterionic π‐propargyl palladium species, affording the desired products in 29% to 95% isolated yields. A plausible reaction mechanism has been also proposed on the basis of control, deuterium labeling experiments and density functional theory (DFT) calculations.

Quantum Dot-Fab' Conjugates as Compact Immunolabels for Microtubule Imaging and Cell Classification.

Antibodies and their conjugates of fluorescent labels are widely applied in life sciences research and clinical pathology. Among diverse label types, compact quantum dots (QDs) provide advantages of multispectral multiplexing, bright signals in the deep red and infrared, and low steric hindrance. However, QD-antibody conjugates have random orientation of the antigen-binding domain which may interfere with labeling and are large (20-30 nm) and heterogeneous, which limits penetration into biospecimens. Here, we develop conjugates of compact QDs and Fab' antibody fragments as primary immunolabels. Fab' fragments are conjugated site-specifically through sulfhydryl groups distal to antigen-binding domains, and the multivalent conjugates have small and homogeneous sizes (∼12 nm) near those of full-sized antibodies. Their performance as immunolabels for intracellular antigens is evaluated quantitatively by metrics of microtubule labeling density and connectivity in fixed cells and for cytological identification in fixed brain specimens, comparing results with probes based on spectrally-matched dyes. QD-Fab' conjugates outperformed QD conjugates of full-sized antibodies and could be imaged with bright signals with 1-photon and 2-photon excitation. The results demonstrate a requirement for smaller bioaffinity agents and site-specific orientation for the success of nanomaterial-based labels to enhance penetration in biospecimens and minimize nonspecific staining.

Long-term intravital subcellular imaging with confocal scanning light-field microscopy.

Long-term observation of subcellular dynamics in living organisms is limited by background fluorescence originating from tissue scattering or dense labeling. Existing confocal approaches face an inevitable tradeoff among parallelization, resolution and phototoxicity. Here we present confocal scanning light-field microscopy (csLFM), which integrates axially elongated line-confocal illumination with the rolling shutter in scanning light-field microscopy (sLFM). csLFM enables high-fidelity, high-speed, three-dimensional (3D) imaging at near-diffraction-limit resolution with both optical sectioning and low phototoxicity. By simultaneous 3D excitation and detection, the excitation intensity can be reduced below 1 mW mm-2, with 15-fold higher signal-to-background ratio over sLFM. We imaged subcellular dynamics over 25,000 timeframes in optically challenging environments in different species, such as migrasome delivery in mouse spleen, retractosome generation in mouse liver and 3D voltage imaging in Drosophila. Moreover, csLFM facilitates high-fidelity, large-scale neural recording with reduced crosstalk, leading to high orientation selectivity to visual stimuli, similar to two-photon microscopy, which aids understanding of neural coding mechanisms.

Tuning multiple enzyme-like activities by metal doping for identification and quantitation of antioxidants in cosmetics

Inspired by the hydrolysis behaviors of skin cells, we exquisitely designed and synthesized a class of hydrolase mimics to develop an analytical method that can both identify and quantity antioxidant components in skin-whitening cosmetics, including ascorbic acid (AA) and its glycoside and phosphate derivatives. A series of ultra-thin Cu1-xMnxO2 or Fe1-yMnyO2 with rich acid-base pairs were prepared via chemical deposition and in-situ CuI/FeII self-assembly. H218O and D216O isotopic labeling studies and density function theory (DFT) calculations were adopted to analyze the cleaving sites of ascorbyl phosphate (AAL)/ascorbyl glucoside (AAP) and confirm that H2O was involved in the new bonds. In-situ DRIFT NH3-IR and −TPD further confirmed that the Fe- or Cu-substitution could increase the quantity and strength of Brønsted and Lewis acid sites. A cascade catalytic fluorescence sensor was designed for selective recognition or quantification of AA and its derivatives, which presents ultra-high-precision (≤2.5 %), stability, and selectivity in testing the target ingredients of five cosmetics from the market. Our nanozymes exhibit higher catalytic efficiency of 17.1 s−1 for AA, 8.42 s−1 for AAL, and 3.32 s−1 for AAP, which are 5.6 ∼ 32.8-fold higher than those of their mimic proteases. This work provides a controllable methodology to design hydrolytic nanozymes, which sheds light on biomimetic engineering and paves the way for breakthroughs in cosmetics industrial applications in the future.

Mapping inhibitory and excitatory projections to the preBӧtzinger complex

Breathing relies on rhythmic activity generated by the preBӧtzinger complex (preBӧtC), a small brainstem region. Because breathing is influenced by many different physiological, behavioral, and emotional contexts, the preBӧtC is not only highly connected with nearby respiratory related regions in the hindbrain, but also has widespread connections with other mid-and forebrain regions not generally implicated in the regulation of breathing. The specific functions for many of these preBӧtC inputs remain unclear. Although afferent pathways indiscriminately target excitatory and inhibitory neurons in the preBӧtC, we hypothesized that inputs to the preBӧtC would map to distinct brain regions based on the inhibitory or excitatory phenotype of the projecting neurons. To test this, mice that express tdTomato only when both Cre and FlpO recombinases are present (Ai65) were bred with mice that express Cre in inhibitory neurons ( VgatCre). Adult offspring ( VgatCre; Ai65) received a unilateral preBӧtC injection of a retrograde AAV that expresses FlpO recombinase (AAVrg-Flpo), thereby specifically activating tdTomato expression in any inhibitory neurons that project directly to the preBӧtC. Whole-brain imaging revealed many labeled neurons along the ipsilateral ventral respiratory column (VRC), far rostral and caudal of the injection site, extending along the intermediate reticular zone (IRt) from the VII nucleus through the caudal end of the ventral respiratory group (VRG). Interestingly, this well-defined and continuous column of labeled neurons was confined to the ventral IRt at its caudal end but moved dorsally at its rostral end. Only a small number of neurons were labeled along the contralateral VRC. Sparse labeling was present in the medial parabrachial, Kolliker-Fuse, and reticular regions of the pons. Many projecting neurons were observed across subregions of the amygdala, which were almost exclusively ipsilateral. The hypothalamus contained diffuse projecting neurons along its rostral-caudal extent that were also mostly ipsilateral. However, denser labeling was present in a distinctly curved cluster of the lateral hypothalamus, which was observed on both the ipsilateral and contralateral side. Consistent with the preBӧtC having distinct inhibitory and excitatory input pathways, we did not observe significant labelling in other regions with known projections to the preBotC identified previously using non-cell-type specific tracing strategies. These included cortex, lateral parabrachial, NTS, and RVM. This will be tested further by replicating this experiment with targeting of glutamatergic ( Vglut2) neurons. Defining these cell-type-specific inputs to the preBӧtC will provide an essential foundation for future functional studies to determine how these circuits may regulate breathing. R01 HL1660317 (Baertsch) R00 HL145004 (Baertsch). This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Label relaxation and shared information for multi-label feature selection

Due to the rapid growth of labels and high-dimensional data, multi-label feature selection has attracted increasing attention. However, two common issues are ignored by existing multi-label feature selection methods: 1) The pseudo-label matrix is constructed by using logical label matrix directly. 2) There is an imbalance of label density in multi-label data. To tackle the mentioned issues, we innovatively propose a new method named Label relaxation and Shared information for Multi-label Feature Selection (LSMFS). Specifically, LSMFS combines a logical label matrix with a non-negative label relaxation matrix to fit a pseudo-label matrix, which is used for learning the correlations of class labels. LSMFS uses the feature weight matrix to capture a shared information of different related labels, which mitigates the influence of low-density labels on feature selection. The above principles are transformed into the objective function of LSMFS, and an alternate iterative optimization algorithm is developed to solve the objective function. Experiments on multi-label datasets from different domains have demonstrated the effectiveness of the proposed method LSMFS. Code is released at https://github.com/HQUF/LSMFS.

Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation

The core of pointly-supervised panoptic segmentation is estimating accurate dense pseudo labels from sparse point labels to train the panoptic head. Previous works generate pseudo labels mainly based on hand-crafted rules, such as connecting multiple points into polygon masks, or assigning the label information of labeled pixels to unlabeled pixels based on the artificially defined traversing distance. The accuracy of pseudo labels is limited by the quality of the hand-crafted rules (polygon masks are rough at object contour regions, and the traversing distance error will result in wrong pseudo labels). To overcome the limitation of hand-crafted rules, we estimate pseudo labels with a fully data-driven pseudo label branch, which is optimized by point labels end-to-end and predicts more accurate pseudo labels than previous methods. We also train an auxiliary semantic branch with point labels, it assists the training of the pseudo label branch by transferring semantic segmentation knowledge through shared parameters. Experiments on Pascal VOC and MS COCO demonstrate that our approach is effective and shows state-of-the-art performance compared with related works. Codes are available at https://github.com/BraveGroup/FDD.